import SonicScrewdriver as utils
import FileCabinet as filecab
# start by loading the hard seeds
stanford = set()
with open('../lexicons/stanford.csv', encoding = 'utf-8') as f:
reader = csv.DictReader(f)
for row in reader:
if row['class'] == 'hard':
stanford.add(row['word'])
sourcedir = '../sourcefiles/'
pairedpaths = filecab.get_pairedpaths(sourcedir, '.tsv')
docids = [x[0] for x in pairedpaths]
wordcounts = filecab.get_wordcounts(sourcedir, '.tsv', docids)
metapath = '../metadata/allgenremeta.csv'
genredict = dict()
datedict = dict()
with open(metapath, encoding = 'utf-8') as f:
reader = csv.DictReader(f)
for row in reader:
date = int(row['firstpub'])
genre = row['genretags']
docid = row['docid']
